学术报告

Stochastic regularization method for linear ill-posed problems

作者:    发布时间:2024-01-02    浏览次数:
报告人: 吕锡亮教授(武汉大学)报告日期:2024年1月3日(星期三)报告时间:10:00-11:00腾讯会议:354-175-615报告摘要:Due to rapid growth of data sizes in practical applications, in recent years stochastic optimization methods have received tremendous attention and proved to be efficient in various applications of science and technology including in particular the machine learning applications. In ...

报告人: 吕锡亮教授(武汉大学)

报告日期:202413日(星期三)

报告时间:10:00-11:00

腾讯会议:354-175-615

报告摘要:

Due to rapid growth of data sizes in practical applications, in recent years stochastic optimization methods have received tremendous attention and proved to be efficient in various applications of science and technology including in particular the machine learning applications. In this talk we propose randomized Kaczmarz method, stochastic gradient descent method and stochastic mirror descent method for solving linear ill-posed inverse problems. The convergence and convergence rate are provided. Several numerical examples validate the efficiency of the proposed algorithms.

报告人简介:

吕锡亮博士,武汉大学数学与统计学院教授。本科毕业于北京大学,并于新加坡国立大学获得硕士、博士学位,曾在马里兰大学、奥地利科学院RICAM研究所从事博士后研究,2010年加入武汉大学数学与统计学院。主要研究方向为反问题理论和计算、机器学习等。